add tokenizer

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

vocab.json

@@ -0,0 +1 @@
+{"n": 0, "c": 1, "s": 2, "k": 3, "g": 4, "t": 5, "z": 6, "l": 7, "i": 8, "'": 9, "h": 10, "f": 11, "w": 12, "m": 13, "y": 14, "r": 15, "b": 16, "u": 17, "o": 19, "a": 20, "v": 21, "p": 22, "’": 23, "e": 24, "j": 25, "d": 26, "|": 18, "[UNK]": 27, "[PAD]": 28}